The observations for the validation were taken from 2015-01-29 to 2023-12-03.
Remember that we have on a daily scale the variables
sfcWind, tas, pr,
tasmax, tasmin and psl and in a
monthly scale clt, rsdt,rsds as a
predictors. We also have the month and the daily daylight amount in
seconds as a predictors too.
| Metric | xgboost | cnn | naive | lstm |
|---|---|---|---|---|
| mae | 16.59 | 20.87 | 23.54 | 19.07 |
| cor | 0.97 | 0.95 | 0.94 | 0.96 |
| ratio_of_sd | 0.96 | 0.95 | 0.94 | 0.97 |
| KGE | 0.95 | 0.93 | 0.92 | 0.95 |
| amplitude_mae_monthly | 22.37 | 20.12 | 32.49 | 21.40 |
| sign_correlation | 0.81 | 0.75 | 0.74 | 0.78 |
| extreme_correlation | 1.00 | 0.77 | 0.78 | 0.92 |
| qqplot_mae | 3.30 | 4.71 | 7.13 | 2.68 |
| acf_mae | 0.05 | 0.04 | 0.06 | 0.04 |
| extremogram_mae | 0.02 | 0.04 | 0.03 | 0.03 |
Important: Right now we are only estimating the upper tail
extremogram. Currently we didn’t find a way to estimate the two tales at
the same time. We are using quant = .97